v1.91.7.0 feat: add functional QA and pre-publication docs checks (#2983)

* feat: add surface-aware exploratory QA and ship documentation gates

* test: preserve delegated QA setup authority after main integration

* fix(qa): clarify exploration order and preserve report artifacts

* test(qa): follow the shared setup reference directly

* refactor(ship): make verification and recovery routes explicit

* test(ship): align evidence and review guards with explicit routes

* fix(workflows): clarify ship recovery and functional QA evidence

* fix(workflows): clarify approval recovery and full QA coverage

* refactor(workflows): order review transactions and clarify ship state

* fix(ship): clarify final verification and fail closed at publication

* fix(evals): attribute native atomic documentation writes

* fix(ship): clarify recovery and documentation lifecycle guidance

* fix(test): preserve observed native placeholder styling in CI

* fix(codex): report watchdog timeouts without a process-exit race

* Checkpoint functional QA implementation and workflow validation repairs

* Fix documentation and shared-review fixture contracts

* docs: clarify judge reuse and evaluation supervision

* test: align review evidence and selected case contracts

* test: verify append-only documentation checkpoints and recovery

* fix: qualify QA workflows and CI validation repairs

* fix: launch shared-libs fixture scripts on Windows

* fix: qualify QA deadlines, fixture isolation, and shard cleanup

* fix: preserve qualified QA and cancellation repairs

* fix: enforce functional fixture authority and share strict event decoding

* fix: retain free-test evidence and explain recovery

* fix: reject malformed native evidence after decoder consolidation

* test: use reliable capture for telemetry privacy filters

* test: refresh measured quick coverage and document validation costs

* Fix native fixture receipts and preserve VM validation evidence

* Align negative judge controls with upstream clarity policy

* Fix report-only QA preparation and public evidence handling

* Clarify QA-only preparation and current-report preservation

* Stream Ship quality judgments with an explicit 64k response contract

* Validate compact judge reasoning locally with supported wire schema

* Align functional QA fixture instructions with evidence acceptance

* Bind native browser diagnostics to execution evidence and align review verdicts

* Preserve native diagnostic line boundaries

* Serialize functional QA evidence from native captures

* Keep large QA evidence fixture payload out of Windows argv

test/plan-create-prepublication.test.ts

@@ -145,21 +145,27 @@ test('count capture assembly retains exact prepublication input through refresh,
   f.hook();const expected=readPendingWriteInput(f.recorder.file,f.expected,f.cwd,f.config,f.startedAt);
   expect(expected).toBeDefined();
   const source=fs.readFileSync(path.join(import.meta.dir,'helpers/claude-pty-runner.ts'),'utf8');
-  const start=source.indexOf('  const capture = (observation: object) => saveSnapshot({',source.indexOf('export async function runPlanSkillCounting('));
-  const end=source.indexOf('\n  });',start);
+  const start=source.indexOf('  const capture = (observation: object) => {',source.indexOf('export async function runPlanSkillCounting('));
+  const end=source.indexOf('\n  function snapshot(',start);
   expect(start).toBeGreaterThan(0);expect(end).toBeGreaterThan(start);
-  const code=new Bun.Transpiler({loader:'ts'}).transformSync(source.slice(start,end+6)+'\nreturn capture;');
-  const capture=new Function('saveSnapshot','opts','ownedFilePermissions','readPendingWriteInput','fixture','session','startedAt','viewport',code)(
+  const code=new Bun.Transpiler({loader:'ts'}).transformSync(source.slice(start,end)+'\nreturn capture;');
+  const capture=new Function('saveSnapshot','opts','ownedFilePermissions','readPendingWriteInput','readPlanCountTranscript','fixture','session','startedAt','viewport',code)(
    createPlanCountSnapshotWriter({EVALS_RUN_ID:'count-prepublication-free',GSTACK_EVAL_DIR:evalDir}),
-   {skillName:'plan-eng-review'},[{file:f.recorder.file,expected:f.expected}],readPendingWriteInput,
+   {skillName:'plan-eng-review'},[{file:f.recorder.file,expected:f.expected}],readPendingWriteInput,readPlanCountTranscript,
    {cwd:f.cwd},{hermeticConfigDir:f.config,rawOutput:()=>f.screen,visibleText:()=>f.screen},f.startedAt,f.screen);
   const progress=capture({state:'in_progress'});
+  expect(progress.artifactError).toBeUndefined();expect(progress.artifactDir).toBeDefined();
+  const initial=JSON.parse(fs.readFileSync(path.join(progress.artifactDir,'observation.json'),'utf8'));
+  expect(initial.state).toBe('in_progress');expect(initial.pendingWriteInputs).toEqual([expected]);expect(initial.publicTools).toEqual([]);
+  const published=f.native('assistant',[f.block()]);f.write([...f.base,published]);
   const thrown=capture({state:'threw',error:'controlled caller interruption'});
   expect(thrown.artifactDir).toBe(progress.artifactDir);expect(thrown.artifactError).toBeUndefined();
   f.close();
   const saved=JSON.parse(fs.readFileSync(path.join(thrown.artifactDir,'observation.json'),'utf8'));
   expect(saved.state).toBe('threw');expect(saved.error).toBe('controlled caller interruption');
   expect(saved.pendingWriteInputs).toEqual([expected]);expect(fs.existsSync(f.recorder.file)).toBe(false);
+  expect(saved.publicTools).toEqual([{sessionId:f.sid,timestamp:published.timestamp,toolUseId:f.id,kind:'use',name:'Write',input:f.input}]);
+  expect(fs.existsSync(f.sidecar)).toBe(false);expect(fs.existsSync(f.journal)).toBe(false);
   expect(fs.readFileSync(path.join(thrown.artifactDir,'terminal.screen.log'),'utf8')).toBe(f.screen);
   expect(fs.statSync(path.join(thrown.artifactDir,'observation.json')).mode&0o777).toBe(0o600);
  }finally{f.close();fs.rmSync(evalDir,{recursive:true,force:true});}